Open Ai Text To Speech1

Provides access to the Open Ai Text To Speech1 API via a configurable MCP bridge.

python

0

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "bach-ai-tools-bachai-open-ai-text-to-speech1": {
      "command": "python",
      "args": [
        "server.py"
      ],
      "env": {
        "API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

This MCP Server provides access to the Open Ai Text To Speech1 API, enabling your applications to convert text to speech through a streamlined, configurable bridge. It supports quick setup, secure API key handling, and flexible run options so you can integrate speech generation into your projects with minimal boilerplate.

How to use

You can run this MCP server locally or via an MCP platform. Use an MCP client to load and start the server, then point your application to the local or remote endpoint provided by the chosen run method. The server exposes a speech endpoint that accepts a model name, input text, and voice parameters to generate audio.

How to install

Prerequisites you need before installation: Python and pip, or the uvx runtime for automatic setup.

# Install the Python package from PyPI (recommended for quick start)
pip install bach-open_ai_text_to_speech1

# Optional: install in editable/development mode if you are developing
# from source you would typically run:
pip install -e .

# Run with uvx (preferred, auto-installs uvx if needed)
uvx --from bach-open_ai_text_to_speech1 bach_open_ai_text_to_speech1

# Or run the latest version explicitly via uvx
uvx --from bach-open_ai_text_to_speech1@latest bach_open_ai_text_to_speech1

# Development mode - direct Python run
python server.py

# After installation, you can also run as a command named using underscores
bach_open_ai_text_to_speech1

Additional configuration and usage notes

API authentication requires an API key. Set the key in your environment before starting the server.

Configuration and environment

Use the following environment variable to provide your API key. You can set this in your shell or in the host environment where the MCP client runs.

export API_KEY="your_api_key_here"

Available tools

speech

Endpoint to generate speech from text. Accepts model name, text input, and voice to produce audio.